Learning grounded word meaning representations on similarity graphs
This work addresses the problem of improving word meaning representations for natural language processing and cognitive modeling, though it appears incremental as it builds on existing graph embedding techniques.
The paper tackled learning visually grounded word meaning representations by introducing HM-SGE, a hierarchical graph embedding model that outperformed state-of-the-art methods in simulating human similarity judgments and concept categorization.
This paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy. The lower level of the hierarchy models modality-specific word representations through dedicated but communicating graphs, while the higher level puts these representations together on a single graph to learn a representation jointly from both modalities. The topology of each graph models similarity relations among words, and is estimated jointly with the graph embedding. The assumption underlying this model is that words sharing similar meaning correspond to communities in an underlying similarity graph in a low-dimensional space. We named this model Hierarchical Multi-Modal Similarity Graph Embedding (HM-SGE). Experimental results validate the ability of HM-SGE to simulate human similarity judgements and concept categorization, outperforming the state of the art.